'Making Taipei City Safer Than Ever' - White Paper MiTAC intelligent CCTV system for TCPD

Document Library
Reference architectures, white papers, and solutions briefs to help build and enhance your network infrastructure, at any level of deployment.
Engagement / Document Library / Optimization of YOLOv4 and YOLOv4-tiny Models with Customized Configurations using Intel® Distribution of OpenVINO™ Toolkit
Optimization of YOLOv4 and YOLOv4-tiny Models with Customized Configurations using Intel® Distribution of OpenVINO™ Toolkit
Optimization of YOLOv4 and YOLOv4-tiny Models with Customized Configurations using Intel® Distribution of OpenVINO™ Toolkit
https://builders-demo.onsumaye.com/solutionslibrary/optimization-of-yolov4-and-yolov4-tiny-models-with-customized-configurations-using-intel-distribution-of-openvino-toolkit
Last Updated: Mar 12, 2025
This document presents two methods for optimizing the YOLOv4 and YOLOv4-tiny models with customized classes and anchors using Intel® Distribution of OpenVINO™ Toolkit. The object detection use case based on the optimized models is used to verify the corresponding inference results. Furthermore, the decreased inference time of the optimized model is demonstrated with the real-time use case of an ISV.
Related Content
I Agree to Share My Information
By submitting this form, you agree to share your personal data with Intel for this business request.
Verify Your Email to Continue
To continue viewing the document, please verify your email address. Check your inbox and follow the instructions.
If you didn’t receive the email, click here to generate a new verification link.
Thank You!
Thanks for registering as a member in the Intel® Industry Solution Builders program. Your account has been activated. Please set your password by clicking on the link sent to your registered email address.
Note: If you do not see an email from our site in your inbox, please check your email account's Spam or Junk folder to ensure the message was not filtered. If the message was filtered, please 'Mark as good' or 'Not spam' or 'Add sender to white-list.'